mm: save soft-dirty bits on swapped pages

Andy Lutomirski reported that if a page with _PAGE_SOFT_DIRTY bit set
get swapped out, the bit is getting lost and no longer available when
pte read back.

To resolve this we introduce _PTE_SWP_SOFT_DIRTY bit which is saved in
pte entry for the page being swapped out.  When such page is to be read
back from a swap cache we check for bit presence and if it's there we
clear it and restore the former _PAGE_SOFT_DIRTY bit back.

One of the problem was to find a place in pte entry where we can save
the _PTE_SWP_SOFT_DIRTY bit while page is in swap.  The _PAGE_PSE was
chosen for that, it doesn't intersect with swap entry format stored in
pte.

Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 6 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dbf61f6174f0..e2d9bdce5e7e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -730,8 +730,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
          * of how soft-dirty works.
          */
         pte_t ptent = *pte;
-        ptent = pte_wrprotect(ptent);
-        ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+        if (pte_present(ptent)) {
+                ptent = pte_wrprotect(ptent);
+                ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+        } else if (is_swap_pte(ptent)) {
+                ptent = pte_swp_clear_soft_dirty(ptent);
+        }
+
         set_pte_at(vma->vm_mm, addr, pte, ptent);
 #endif
 }
@@ -752,14 +758,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
         pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
         for (; addr != end; pte++, addr += PAGE_SIZE) {
                 ptent = *pte;
-                if (!pte_present(ptent))
-                        continue;
 
                 if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
                         clear_soft_dirty(vma, addr, pte);
                         continue;
                 }
 
+                if (!pte_present(ptent))
+                        continue;
+
                 page = vm_normal_page(vma, addr, ptent);
                 if (!page)
                         continue;
@@ -930,8 +937,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
                 flags = PM_PRESENT;
                 page = vm_normal_page(vma, addr, pte);
         } else if (is_swap_pte(pte)) {
-                swp_entry_t entry = pte_to_swp_entry(pte);
-
+                swp_entry_t entry;
+                if (pte_swp_soft_dirty(pte))
+                        flags2 |= __PM_SOFT_DIRTY;
+                entry = pte_to_swp_entry(pte);
                 frame = swp_type(entry) |
                         (swp_offset(entry) << MAX_SWAPFILES_SHIFT);
                 flags = PM_SWAP;